+1 — hitting this and a couple of related issues with the Zoom for Claude connector. Adding repro details in case it helps the team scope the fix.
Environment
- Zoom for Claude connector, accessed via Claude Code MCP namespace
mcp__claude_ai_Zoom_for_Claude__*
- Commercial Zoom (not Gov), AI Companion enabled, no cloud recording
- Meetings are AI-Companion-transcribed (transcripts visible in Zoom Workplace Hub → My notes → Transcript widget)
Symptom 1 — get_file_content returns empty for every My Notes doc
search_zoom with entity_type: "zoom_doc" and doc_view: "notes" returns a populated list of My Notes docs with valid file_id values, plausible create_time / modify_time deltas (~20–45 min between create and last modify, consistent with meeting duration), and working docs.zoom.us/doc/<file_id> links. The Zoom Workplace UI shows full content (note body and Transcript widget) for these docs.
But get_file_content returns {"file_content": "\n", "file_name": "..."} for every one of them. Tested across multiple notes from today and from earlier in the week — same result.
The tool description states “This tool works for both Docs and My Notes,” so this looks like a real bug, not an unsupported capability. Likely cause: the connector is hitting a synchronous content endpoint without going through the export job flow (POST /docs/files/{fileId}/export → poll /docs/exports/{exportId}/status → GET /docs/files/{fileId}/content), which appears to be required for note-shaped Workplace content.
Symptom 2 — search_meetings returns empty even when meetings exist
search_meetings(from=<this week start>, to=<today>) → {"meetings": [], "page_size": 30, "has_more": false}
search_meetings(no filters, page_size=30) → {"meetings": [], "has_more": false}
search_meetings(from=today, to=today+1, include_zoom_my_notes=true) → {"meetings": []}
Same account, same time window, search_zoom(zoom_doc, doc_view: notes) returns 10+ meeting note docs from today alone. So the meetings clearly exist; search_meetings just isn’t seeing them. This blocks get_meeting_assets and get_recording_resource because both need a meeting UUID and there’s no other way to enumerate them through the connector.
Symptom 3 — chat search empty
search_zoom(entity_type: chat, page_size: 5) → {"data": []}
Probably out of scope for this thread, but listing for completeness.
What does work
search_zoom with entity_type: "zoom_doc" (any doc_view)recordings_list (returns empty, but plausibly genuine — no cloud recording on this account)
Net effect
The “hand the assistant my Zoom transcripts and let it summarize / answer questions” flow that’s the obvious value prop of this connector is currently impossible end-to-end on an AI-Companion-only account: there’s no path from “what meetings did I have” → “give me the transcript text.” Each broken link has a separate symptom but they compound.
Happy to share specific tool-call payloads privately if useful.
